SmophyAI

Published daily · Next update 02:00 UTC

xAI · Grok family

SpaceXAI: Grok 4.5

SpaceXAI: Grok 4.5 ranks #9 of 85 models by Artificial Analysis quality score (55.8) at $3.00/1M tokens blended - and ranks #30 of 291 by average real OpenRouter usage share over the trailing 35-day window (0.65%). Available from 1 provider at up to 100.0% uptime.

  1. Quality (Intelligence Index) - 55.8
  2. Coding index - 72.4
  3. Agentic index - 48.9
  4. Price (blended $/1M) - 3.00
  5. Context window - 500,000
  6. Usage rank - #30 of 291
  7. Providers - 1
  8. Open/closed - closed
Provider reliability →Compare Grok versions →

Usage share over time

1.27%0.95%0.64%0.32%0.00%Share of usageJul 9Jul 24Aug 8

Compare SpaceXAI: Grok 4.5

vs OpenAI: GPT-5.6 Sol (batch) →vs Claude Opus 5 (batch) →vs Google: Gemini 3.5 Flash (batch) →vs DeepSeek: DeepSeek V4 Flash 0423 →

Frequently asked questions

What is SpaceXAI: Grok 4.5's quality score?

SpaceXAI: Grok 4.5 scores 55.8 on Artificial Analysis's Intelligence Index, ranking #9 of 85 models with a published score.

How much does SpaceXAI: Grok 4.5 cost?

SpaceXAI: Grok 4.5 costs $3.00 per 1M tokens (blended 75% prompt / 25% completion pricing).

Is SpaceXAI: Grok 4.5 widely used?

SpaceXAI: Grok 4.5 ranks #30 of 291 models by average real OpenRouter usage share, averaging 0.65% of classified token volume over the trailing 35-day window.

Is SpaceXAI: Grok 4.5 open-weight or closed?

SpaceXAI: Grok 4.5 is a closed-weight model.

Source: OpenRouter (openrouter.ai/rankings), as of August 9, 2026.

Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Methodology: smophy.ai/benchmark/methodology

Token counts originate from each provider's own tokenizer and are not directly comparable across providers.